001/*
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018package org.apache.hadoop.hbase.mapreduce;
019
020import java.io.IOException;
021import java.util.Arrays;
022import java.util.Collections;
023import java.util.Map;
024import java.util.Objects;
025import java.util.Set;
026import java.util.TreeMap;
027import java.util.stream.Collectors;
028import org.apache.hadoop.conf.Configuration;
029import org.apache.hadoop.hbase.HRegionLocation;
030import org.apache.hadoop.hbase.RegionMetrics;
031import org.apache.hadoop.hbase.ServerName;
032import org.apache.hadoop.hbase.Size;
033import org.apache.hadoop.hbase.client.Admin;
034import org.apache.hadoop.hbase.client.RegionLocator;
035import org.apache.hadoop.hbase.util.Bytes;
036import org.apache.yetus.audience.InterfaceAudience;
037import org.slf4j.Logger;
038import org.slf4j.LoggerFactory;
039
040/**
041 * Computes size of each region for given table and given column families. The value is used by
042 * MapReduce for better scheduling.
043 */
044@InterfaceAudience.Private
045public class RegionSizeCalculator {
046
047  private static final Logger LOG = LoggerFactory.getLogger(RegionSizeCalculator.class);
048
049  /**
050   * Maps each region to its size in bytes.
051   */
052  private final Map<byte[], Long> sizeMap = new TreeMap<>(Bytes.BYTES_COMPARATOR);
053
054  static final String ENABLE_REGIONSIZECALCULATOR = "hbase.regionsizecalculator.enable";
055  private static final long MEGABYTE = 1024L * 1024L;
056
057  /**
058   * Computes size of each region for table and given column families.
059   */
060  public RegionSizeCalculator(RegionLocator regionLocator, Admin admin) throws IOException {
061    init(regionLocator, admin);
062  }
063
064  private void init(RegionLocator regionLocator, Admin admin) throws IOException {
065    if (!enabled(admin.getConfiguration())) {
066      LOG.info("Region size calculation disabled.");
067      return;
068    }
069
070    if (regionLocator.getName().isSystemTable()) {
071      LOG.info("Region size calculation disabled for system tables.");
072      return;
073    }
074
075    LOG.info("Calculating region sizes for table \"" + regionLocator.getName() + "\".");
076
077    // Get the servers which host regions of the table
078    Set<ServerName> tableServers = getRegionServersOfTable(regionLocator);
079
080    for (ServerName tableServerName : tableServers) {
081      for (RegionMetrics regionLoad : admin.getRegionMetrics(tableServerName,
082        regionLocator.getName())) {
083
084        byte[] regionId = regionLoad.getRegionName();
085        long regionSizeBytes =
086          ((long) regionLoad.getStoreFileSize().get(Size.Unit.MEGABYTE)) * MEGABYTE;
087
088        sizeMap.put(regionId, regionSizeBytes);
089
090        if (LOG.isDebugEnabled()) {
091          LOG.debug("Region " + regionLoad.getNameAsString() + " has size " + regionSizeBytes);
092        }
093      }
094    }
095    LOG.debug("Region sizes calculated");
096  }
097
098  private Set<ServerName> getRegionServersOfTable(RegionLocator regionLocator) throws IOException {
099    // The region locations could contain `null` ServerName instances if the region is currently
100    // in transition, we filter those out for now, which impacts the size calculation for these
101    // regions temporarily until the ServerName gets filled in later
102    return regionLocator.getAllRegionLocations().stream().map(HRegionLocation::getServerName)
103      .filter(Objects::nonNull).collect(Collectors.toSet());
104  }
105
106  boolean enabled(Configuration configuration) {
107    return configuration.getBoolean(ENABLE_REGIONSIZECALCULATOR, true);
108  }
109
110  /**
111   * Returns size of given region in bytes. Returns 0 if region was not found.
112   */
113  public long getRegionSize(byte[] regionId) {
114    Long size = sizeMap.get(regionId);
115    if (size == null) {
116      LOG.debug("Unknown region:" + Arrays.toString(regionId));
117      return 0;
118    } else {
119      return size;
120    }
121  }
122
123  public Map<byte[], Long> getRegionSizeMap() {
124    return Collections.unmodifiableMap(sizeMap);
125  }
126}